A Collaborative Multi-Agent Model for Database Parameter Tuning

LI Jiang-min; QIAO Shao-jie; HAN Nan; WU Tao; GAO Rui-wei; PENG Yu-han; XIE Tian-cheng; RAN Li-qiong

doi:10.12263/DZXB.20230724

您当前的位置：

首页 >

文章列表页 >

A Collaborative Multi-Agent Model for Database Parameter Tuning

PAPERS | 更新时间：2025-12-11

- A Collaborative Multi-Agent Model for Database Parameter Tuning
- ACTA ELECTRONICA SINICA Vol. 52, Issue 11, Pages: 3751-3756(2024)
- 作者机构：
  
  1.成都信息工程大学软件工程学院，四川成都 610225
  2.成都信息工程大学管理学院，四川成都 610103
  3.重庆邮电大学网络空间安全与信息法学院，重庆 400065
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(62272066);Sichuan Science and Technology Program(2021JDJQ0021;2022YFG0186;2022NSFSC0511;2023YFG0027);Planning Foundation for Humanities and Social Sciences of Ministry of Education of China(22YJAZH088)
- DOI：10.12263/DZXB.20230724
  CLC： TP311
- Received：02 August 2023，
  
  Revised：2024-02-07，
  
  Published：25 November 2024
- 稿件说明：
移动端阅览
李江敏, 乔少杰, 韩楠, 等. 面向数据库参数调优的协作型多智能体模型[J]. 电子学报, 2024, 52(11): 3751-3756.

LI Jiang-min, QIAO Shao-jie, HAN Nan, et al. A Collaborative Multi-Agent Model for Database Parameter Tuning[J]. Acta Electronica Sinica, 2024, 52(11): 3751-3756.
李江敏, 乔少杰, 韩楠, 等. 面向数据库参数调优的协作型多智能体模型[J]. 电子学报, 2024, 52(11): 3751-3756. DOI：10.12263/DZXB.20230724

LI Jiang-min, QIAO Shao-jie, HAN Nan, et al. A Collaborative Multi-Agent Model for Database Parameter Tuning[J]. Acta Electronica Sinica, 2024, 52(11): 3751-3756. DOI：10.12263/DZXB.20230724

摘要

数据库参数调优是提高数据库性能的重要任务之一.数据库参数可按照作用域范围和功能进行分类，探究某一类参数之间的相互影响以及不同类别之间的相互影响是非常重要的，但是现有方法尚未考虑这一方面.提出面向数据库参数调优的协作型多智能体模型DBT-MADDPG（DataBase Tuning-Multi-Agent Deep Deterministic Policy Gradient），设计单智能体预训练模型SA（Single Agent）、多智能体联合训练模型JAM（Joint Action Model）以及基于概率选择的联合训练模型JAPM（Joint Action Probability Model），分阶段对数据库参数进行调优.实验结果表明，DBT-MADDPG模型能够分功能、分参数级别对数据库参数进行调优，在SA模型训练阶段便能到达主流算法的性能，且比主流算法快17.85%获得较佳配置.

Abstract

Database parameter tuning is one of the crucial tasks in improving the performance of database systems. Database parameters can be classified based on their scopes and functionalities. It plays an essential role in investigating the mutual influence of parameters within a specific category or between different categories. But

the existing methods do not take into consideration this aspect. A collaborative multi-agent model called DBT-MADDPG (DataBase Tuning-Multi-Agent Deep Deterministic Policy Gradient) is proposed for database parameter tuning. A single-agent pre-training model called SA (Single Agent)

a multi-agent joint training model called JAM (Joint Action Model)

and a joint training model based on probabilistic selection called JAPM (Joint Action Probability Model) are designed for tuning the database parameters at different stages. The experimental results show that the DBT-MADDPG model is capable of tuning the database parameters at different functional and parameter levels

and can reach the performance of mainstream algorithms in the training stage of the SA model

and is 17.85% faster than the state-of-the-art algorithms to obtain the optimal configuration.

关键词

Keywords

references

李国良 , 周煊赫 , 孙佶 , 等 . 基于机器学习的数据库技术综述 [J ] . 计算机学报 , 2020 , 43 ( 11 ): 2019 - 2049 .

LI G L , ZHOU X H , SUN J , et al . A survey of machine learning based database techniques [J ] . Chinese Journal of Computers , 2020 , 43 ( 11 ): 2019 - 2049 . (in Chinese)

ZHAO X Y , ZHOU X H , LI G L . Automatic database knob tuning: A survey [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 12 ): 12470 - 12490 .

CEREDA S , VALLADARES S , CREMONESI P , et al . CGPTuner [J ] . Proceedings of the VLDB Endowment , 2021 , 14 ( 8 ): 1401 - 1413 .

ZHU Y Q , LIU J X , GUO M Y , et al . BestConfig: Tapping the performance potential of systems via automatic configuration tuning [C ] // Proceedings of the 2017 Symposium on Cloud Computing . New York : ACM , 2017 : 338 - 350 .

ZHANG B , VAN AKEN D , WANG J , et al . A demonstration of the ottertune automatic database management system tuning service [J ] . Proceedings of the VLDB Endowment , 2018 , 11 ( 12 ): 1910 - 1913 .

李维刚 , 甘平 , 谢璐 , 等 . 基于样本对元学习的小样本图像分类方法 [J ] . 电子学报 , 2022 , 50 ( 2 ): 295 - 304 .

LI W G , GAN P , XIE L , et al . A few-shot image classification method by pairwise-based meta learning [J ] . Acta Electronica Sinica , 2022 , 50 ( 2 ): 295 - 304 . (in Chinese)

ZHANG X Y , WU H , CHANG Z , et al . ResTune: Resource oriented tuning boosted by meta-learning for cloud databases [C ] // Proceedings of the 2021 International Conference on Management of Data . New York : ACM , 2021 : 2102 - 2114 .

LI G L , ZHOU X H , LI S F , et al . QTune [J ] . Proceedings of the VLDB Endowment , 2019 , 12 ( 12 ): 2118 - 2130 .

ZHANG J , LIU Y , ZHOU K , et al . An end-to-end automatic cloud database tuning system using deep reinforcement learning [C ] // Proceedings of the 2019 International Conference on Management of Data . New York : ACM , 2019 : 415 - 432 .

TAN J , ZHANG T , LI F , et al . iBTune: Individualized buffer tuning for large-scale cloud databases [J ] . Proceedings of the VLDB Endowment , 2019 , 12 ( 10 ): 1221 - 1234 .

DUAN S , THUMMALA V , BABU S . Tuning database configuration parameters with iTuned [J ] . Proceedings of the VLDB Endowment , 2009 , 2 ( 1 ): 1246 - 1257 .

KANELLIS K , DING C , KROTH B , et al . LlamaTune [J ] . Proceedings of the VLDB Endowment , 2022 , 15 ( 11 ): 2953 - 2965 .

LOWE R , WU Y , TAMAR A , et al . Multi-agent actor-critic for mixed cooperative-competitive environments [C ] // Proceedings of the 31st International Conference on Neural Information Processing Systems . New York : ACM , 2017 : 6382 - 6393 .

肖硕 , 黄珍珍 , 张国鹏 , 等 . 基于SAC的多智能体深度强化学习算法 [J ] . 电子学报 , 2021 , 49 ( 9 ): 1675 - 1681 .

XIAO S , HUANG Z Z , ZHANG G P , et al . Deep reinforcement learning algorithm of multi-agent based on SAC [J ] . Acta Electronica Sinica , 2021 , 49 ( 9 ): 1675 - 1681 . (in Chinese)

饶宁 , 许华 , 蒋磊 , 等 . 基于多智能体深度强化学习的分布式协同干扰功率分配算法 [J ] . 电子学报 , 2022 , 50 ( 6 ): 1319 - 1330 .

RAO N , XU H , JIANG L , et al . Allocation algorithm of distributed cooperative jamming power based on multi-agent deep reinforcement learning [J ] . Acta Electronica Sinica , 2022 , 50 ( 6 ): 1319 - 1330 . (in Chinese)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved PBS Multi-Agent Path Planning Algorithm Based on Conflict Cost Bayesian Weighting

Advance into Ocean: From Bionic Monomer to Swarm Intelligence

A Strategy to Form Agent Coalition Based on Encouragement

Related Author

ZHANG Jin-bao

GONG De-zheng

ZHOU Wen-na

LI Rui-qi

MAO Jian-lin

QIAN Cheng-ze

WANG Jing-jing

CHEN Jian-rui

Related Institution

Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology

Faculty of Information Engineering and Automation, Kunming University of Science and Technology

Department of Electronic Engineering, Tsinghua University

Department of Computer Beijing Institute of Meteorology Beijing China

National Engineering Laboratory for Disaster Backup and Recovery, Beijing University of Posts and Telecommunications.

⁰